相关论文: A Self-Supervised Paradigm for Data-Efficient Medi…

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper…

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains…

In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and…

Pretraining data selection has the potential to improve language model pretraining efficiency by utilizing higher-quality data from massive web data corpora. Current data selection methods, which rely on either hand-crafted rules or larger…

Self-supervised pretraining attempts to enhance model performance by obtaining effective features from unlabeled data, and has demonstrated its effectiveness in the field of histopathology images. Despite its success, few works concentrate…

Recently, the robotics community has amassed ever larger and more diverse datasets to train generalist robot policies. However, while these policies achieve strong mean performance across a variety of tasks, they often underperform on…

A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size. Consequently, we…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

Can a small amount of verified goal information steer the expensive self-supervised pretraining of foundation models? Standard pretraining optimizes a fixed proxy objective (e.g., next-token prediction), which can misallocate compute away…

The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications. As a result, constructing high-performance 3D convolutional neural networks from…

Recent breakthroughs in self-supervised learning have enabled the use of large unlabeled datasets to train visual foundation models that can generalize to a variety of downstream tasks. While this training paradigm is well suited for the…

Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which mainly requires instruction datasets to enable model…

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…

Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…

Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application, machines are expected to understand images like human.…

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

Scaling up model and data size have demonstrated impressive performance improvement over a wide range of tasks. Despite extensive studies on scaling behaviors for general-purpose tasks, medical images exhibit substantial differences from…

In the medical domain, acquiring large datasets poses significant challenges due to privacy concerns. Nonetheless, the development of a robust deep-learning model for retinal disease diagnosis necessitates a substantial dataset for…

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods…

Pre-training has shown success in different areas of machine learning, such as Computer Vision (CV), Natural Language Processing (NLP) and medical imaging. However, it has not been fully explored for clinical data analysis. Even though an…